@wentorai/research-plugins 1.0.0 → 1.2.0

package/skills/literature/fulltext/osf-api/SKILL.md

@@ -0,0 +1,212 @@
+---
+name: osf-api
+description: "Manage open science projects and preprints via the OSF REST API"
+metadata:
+  openclaw:
+    emoji: "🔓"
+    category: "literature"
+    subcategory: "fulltext"
+    keywords: ["OSF", "Open Science Framework", "preprints", "open data", "reproducibility", "COS"]
+    source: "https://osf.io/"
+---
+
+# OSF (Open Science Framework) API
+
+## Overview
+
+The Open Science Framework by the Center for Open Science provides infrastructure for the entire research lifecycle — project management, file storage, preprint hosting, and registrations. The API enables search, project creation, file management, and preprint discovery across OSF Preprints, PsyArXiv, SocArXiv, and 25+ community preprint servers. Free, no auth for read access.
+
+## API Endpoints
+
+### Base URL
+
+```
+https://api.osf.io/v2
+```
+
+### Search
+
+```bash
+# Search across all OSF content
+curl "https://api.osf.io/v2/search/?q=replication+crisis&page[size]=20"
+
+# Search preprints
+curl "https://api.osf.io/v2/preprints/?filter[q]=machine+learning&page[size]=20"
+
+# Filter by preprint provider
+curl "https://api.osf.io/v2/preprints/?filter[provider]=psyarxiv&filter[q]=cognitive+bias"
+
+# Search registrations (pre-registered studies)
+curl "https://api.osf.io/v2/registrations/?filter[q]=randomized+controlled+trial"
+```
+
+### Projects
+
+```bash
+# Get public projects
+curl "https://api.osf.io/v2/nodes/?filter[public]=true&filter[q]=neuroimaging"
+
+# Get project details
+curl "https://api.osf.io/v2/nodes/{node_id}/"
+
+# Get project files
+curl "https://api.osf.io/v2/nodes/{node_id}/files/"
+
+# Get project contributors
+curl "https://api.osf.io/v2/nodes/{node_id}/contributors/"
+```
+
+### Preprint Providers
+
+| Provider | Filter | Disciplines |
+|----------|--------|-------------|
+| OSF Preprints | `osf` | Multidisciplinary |
+| PsyArXiv | `psyarxiv` | Psychology |
+| SocArXiv | `socarxiv` | Social sciences |
+| EarthArXiv | `eartharxiv` | Earth sciences |
+| BioHackrXiv | `biohackrxiv` | Bioinformatics |
+| engrXiv | `engrxiv` | Engineering |
+| MedArXiv | `medarxiv` | Medical sciences |
+| NutriXiv | `nutrixiv` | Nutrition |
+
+### Query Parameters
+
+| Parameter | Description | Example |
+|-----------|-------------|---------|
+| `filter[q]` | Text search | `filter[q]=open+data` |
+| `filter[provider]` | Preprint server | `filter[provider]=psyarxiv` |
+| `filter[subjects]` | Subject filter | Subject taxonomy ID |
+| `filter[date_created]` | Date filter | `filter[date_created][gte]=2024-01-01` |
+| `page[size]` | Results per page (max 100) | `page[size]=50` |
+| `page` | Page number | `page=2` |
+
+## Response Structure (Preprint)
+
+```json
+{
+  "data": [
+    {
+      "id": "abc12",
+      "type": "preprints",
+      "attributes": {
+        "title": "Replication of the Ego Depletion Effect",
+        "description": "We attempted to replicate...",
+        "date_created": "2024-06-15T10:00:00Z",
+        "date_published": "2024-06-16T08:00:00Z",
+        "doi": "10.31234/osf.io/abc12",
+        "is_published": true,
+        "subjects": [["Social and Behavioral Sciences", "Psychology"]],
+        "tags": ["replication", "ego depletion"]
+      },
+      "relationships": {
+        "contributors": {"links": {"related": {"href": "..."}}},
+        "primary_file": {"links": {"related": {"href": "..."}}}
+      }
+    }
+  ]
+}
+```
+
+## Python Usage
+
+```python
+import requests
+
+BASE_URL = "https://api.osf.io/v2"
+
+
+def search_preprints(query: str, provider: str = None,
+                     page_size: int = 20) -> list:
+    """Search OSF preprints across providers."""
+    params = {
+        "filter[q]": query,
+        "page[size]": page_size,
+    }
+    if provider:
+        params["filter[provider]"] = provider
+
+    resp = requests.get(f"{BASE_URL}/preprints/", params=params)
+    resp.raise_for_status()
+    data = resp.json()
+
+    results = []
+    for item in data.get("data", []):
+        attrs = item.get("attributes", {})
+        results.append({
+            "id": item.get("id"),
+            "title": attrs.get("title"),
+            "description": (attrs.get("description") or "")[:300],
+            "doi": attrs.get("doi"),
+            "date": attrs.get("date_published", "")[:10],
+            "tags": attrs.get("tags", []),
+            "url": f"https://osf.io/{item.get('id')}/",
+        })
+    return results
+
+
+def search_registrations(query: str,
+                         page_size: int = 20) -> list:
+    """Search pre-registered studies on OSF."""
+    params = {
+        "filter[q]": query,
+        "page[size]": page_size,
+    }
+    resp = requests.get(f"{BASE_URL}/registrations/", params=params)
+    resp.raise_for_status()
+    data = resp.json()
+
+    results = []
+    for item in data.get("data", []):
+        attrs = item.get("attributes", {})
+        results.append({
+            "id": item.get("id"),
+            "title": attrs.get("title"),
+            "description": (attrs.get("description") or "")[:300],
+            "date_registered": attrs.get("date_registered", "")[:10],
+            "registration_schema": attrs.get("registration_supplement"),
+        })
+    return results
+
+
+def get_project_files(node_id: str) -> list:
+    """List files in an OSF project."""
+    resp = requests.get(f"{BASE_URL}/nodes/{node_id}/files/")
+    resp.raise_for_status()
+    data = resp.json()
+
+    providers = []
+    for item in data.get("data", []):
+        attrs = item.get("attributes", {})
+        providers.append({
+            "provider": attrs.get("provider"),
+            "name": attrs.get("name"),
+        })
+    return providers
+
+
+# Example: search psychology preprints
+preprints = search_preprints("cognitive load", provider="psyarxiv")
+for p in preprints[:5]:
+    print(f"[{p['date']}] {p['title']}")
+    print(f"  DOI: {p['doi']}")
+
+# Example: find pre-registered clinical trials
+regs = search_registrations("randomized placebo")
+for r in regs[:5]:
+    print(f"[{r['date_registered']}] {r['title']}")
+```
+
+## Use Cases
+
+1. **Preprint discovery**: Search across 25+ preprint servers
+2. **Pre-registration search**: Find registered study protocols
+3. **Open data access**: Download shared research datasets
+4. **Reproducibility**: Access materials, data, and code for published studies
+5. **Project management**: Programmatic project and file management
+
+## References
+
+- [OSF](https://osf.io/)
+- [OSF API Documentation](https://developer.osf.io/)
+- [OSF Preprints](https://osf.io/preprints/)
+- [Center for Open Science](https://cos.io/)

package/skills/literature/fulltext/pmc-ftp-bulk-download/SKILL.md

@@ -0,0 +1,182 @@
+---
+name: pmc-ftp-bulk-download
+description: "Bulk download PMC Open Access articles via FTP for large-scale mining"
+metadata:
+  openclaw:
+    emoji: "📦"
+    category: "literature"
+    subcategory: "fulltext"
+    keywords: ["pmc", "bulk download", "ftp", "text mining", "open access", "pubmed central"]
+    source: "https://www.ncbi.nlm.nih.gov/pmc/tools/ftp/"
+---
+
+# PMC FTP Bulk Download
+
+## Overview
+
+The PMC FTP Service provides bulk download access to millions of full-text articles from PubMed Central's Open Access Subset. Unlike the single-article APIs (E-utilities, BioC), the FTP service is designed for large-scale corpus construction — downloading entire collections for text mining, NLP training, systematic reviews, and bibliometric analysis. Free, no authentication required.
+
+**Note**: PMC is migrating to AWS-based Cloud Service in August 2026. FTP paths may change; check official docs for updates.
+
+## FTP Access Points
+
+### Connection
+
+```bash
+# FTP (classic)
+ftp ftp.ncbi.nlm.nih.gov
+# Navigate to: /pub/pmc
+
+# HTTPS alternative (recommended)
+# Base: https://ftp.ncbi.nlm.nih.gov/pub/pmc/
+```
+
+### Available Datasets
+
+| Dataset | Path | Content | Format |
+|---------|------|---------|--------|
+| **OA Commercial** | `/pub/pmc/oa_comm/` | CC BY/CC0 articles (commercial use OK) | .tar.gz packages |
+| **OA Non-Commercial** | `/pub/pmc/oa_noncomm/` | CC BY-NC articles | .tar.gz packages |
+| **OA Other** | `/pub/pmc/oa_other/` | Other open licenses | .tar.gz packages |
+| **Author Manuscripts** | `/pub/pmc/manuscript/` | NIH-funded manuscripts | .tar.gz packages |
+| **Historical OCR** | `/pub/pmc/historical_ocr/` | Pre-digital scanned articles | .tar.gz |
+| **File lists** | `/pub/pmc/oa_file_list.csv` | Index of all OA articles | CSV |
+
+### File List Index
+
+Download the master index to plan your downloads:
+
+```bash
+# Download the OA file list (CSV, ~200MB)
+wget https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_file_list.csv
+
+# CSV columns:
+# File, Article Citation, AccessionID, LastUpdated, PMID, License
+```
+
+## Download Strategies
+
+### Strategy 1: Download Specific Articles
+
+```python
+import requests
+import tarfile
+import io
+import csv
+
+def download_article_package(pmcid: str, base_url: str = "https://ftp.ncbi.nlm.nih.gov/pub/pmc"):
+    """Download and extract a specific PMC article package."""
+    # First, look up the file path from the file list
+    # (In practice, you'd load this once and index by PMCID)
+    file_list_url = f"{base_url}/oa_file_list.csv"
+    # ... lookup pmcid in file list to get path ...
+
+    # Download the tar.gz package
+    resp = requests.get(f"{base_url}/{file_path}", stream=True)
+    resp.raise_for_status()
+
+    # Extract
+    with tarfile.open(fileobj=io.BytesIO(resp.content), mode="r:gz") as tar:
+        tar.extractall(path=f"./articles/{pmcid}")
+    print(f"Extracted {pmcid}")
+```
+
+### Strategy 2: Bulk Download by License
+
+```bash
+#!/bin/bash
+# Download all commercial-use articles (CC BY / CC0)
+# WARNING: This is ~100GB+ compressed
+
+mkdir -p pmc_corpus/commercial
+cd pmc_corpus/commercial
+
+# Download the baseline (all current articles)
+wget -r -np -nH --cut-dirs=3 \
+  https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_comm/xml/
+
+# Incremental updates (run periodically)
+wget -r -np -nH --cut-dirs=3 -N \
+  https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_comm/xml/
+```
+
+### Strategy 3: Filtered Download via File List
+
+```python
+import csv
+import requests
+from pathlib import Path
+
+def download_filtered_corpus(file_list_path: str, output_dir: str,
+                              license_filter: str = "CC BY",
+                              max_articles: int = 1000):
+    """Download articles matching a license filter."""
+    output = Path(output_dir)
+    output.mkdir(parents=True, exist_ok=True)
+    base = "https://ftp.ncbi.nlm.nih.gov/pub/pmc"
+    downloaded = 0
+
+    with open(file_list_path) as f:
+        reader = csv.DictReader(f)
+        for row in reader:
+            if license_filter and license_filter not in row.get("License", ""):
+                continue
+            if downloaded >= max_articles:
+                break
+
+            file_path = row["File"]
+            url = f"{base}/{file_path}"
+            local_path = output / Path(file_path).name
+
+            if local_path.exists():
+                continue
+
+            resp = requests.get(url, stream=True, timeout=60)
+            if resp.status_code == 200:
+                local_path.write_bytes(resp.content)
+                downloaded += 1
+                if downloaded % 100 == 0:
+                    print(f"Downloaded {downloaded} articles...")
+
+    print(f"Total downloaded: {downloaded}")
+```
+
+## PMC ID Cross-Referencing
+
+Convert between different article identifiers:
+
+```bash
+# PMID → PMCID → DOI conversion
+curl "https://www.ncbi.nlm.nih.gov/pmc/utils/idconv/v1.0/?ids=29346600&format=json"
+
+# Batch conversion (up to 200 IDs)
+curl "https://www.ncbi.nlm.nih.gov/pmc/utils/idconv/v1.0/?ids=29346600,30266829,31048553&format=json"
+```
+
+## Package Contents
+
+Each article package (.tar.gz) typically contains:
+
+```
+PMC1234567/
+├── PMC1234567.xml       # Full text in JATS XML
+├── PMC1234567.pdf       # PDF (if available)
+├── figure1.jpg          # Figures
+├── figure2.jpg
+├── table1.html          # Tables (sometimes)
+└── supplement1.pdf      # Supplementary materials
+```
+
+## Best Practices
+
+- **Start with the file list**: Download `oa_file_list.csv` first and filter locally
+- **Respect rate limits**: Space requests 0.3s apart for individual downloads
+- **Use incremental updates**: After initial download, use `-N` flag to only get new/updated files
+- **Check licenses**: OA Commercial (CC BY) allows any use; Non-Commercial restricts commercial applications
+- **Storage planning**: Full OA Subset is ~500GB+ uncompressed
+
+## References
+
+- [PMC FTP Documentation](https://www.ncbi.nlm.nih.gov/pmc/tools/ftp/)
+- [PMC Open Access Subset](https://www.ncbi.nlm.nih.gov/pmc/tools/openftlist/)
+- [PMC ID Converter API](https://www.ncbi.nlm.nih.gov/pmc/tools/id-converter-api/)

package/skills/literature/fulltext/zotero-ai-butler-guide/SKILL.md

@@ -0,0 +1,166 @@
+---
+name: zotero-ai-butler-guide
+description: "AI-powered paper summarization plugin for Zotero"
+metadata:
+  openclaw:
+    emoji: "🤵"
+    category: "literature"
+    subcategory: "fulltext"
+    keywords: ["Zotero", "AI summary", "paper summarization", "LLM", "abstract generation", "reading assistant"]
+    source: "https://github.com/steven-jianhao-li/zotero-AI-Butler"
+---
+
+# Zotero AI Butler Guide
+
+## Overview
+
+Zotero AI Butler is a Zotero plugin that uses LLMs to summarize, analyze, and annotate academic papers directly within Zotero. It can generate structured summaries, extract key findings, compare papers, and answer questions about documents — all without leaving the reference manager. Supports multiple LLM backends (OpenAI, Claude, local models).
+
+## Installation
+
+```bash
+# Download .xpi from GitHub releases
+# Zotero 7: Tools → Add-ons → Install Add-on From File
+```
+
+## Configuration
+
+```markdown
+### LLM Backend Setup (Preferences → AI Butler)
+
+**Option 1: OpenAI**
+- Provider: OpenAI
+- Model: gpt-4o
+- Set environment variable for credentials
+
+**Option 2: Anthropic**
+- Provider: Anthropic
+- Model: claude-sonnet-4-20250514
+
+**Option 3: Local (Ollama)**
+- Provider: Ollama
+- Endpoint: http://localhost:11434
+- Model: llama3.1
+
+**Option 4: Custom API**
+- Provider: Custom
+- Endpoint: your-api-url
+- Compatible with OpenAI API format
+```
+
+## Features
+
+### Paper Summarization
+
+```markdown
+### Usage
+1. Select paper in Zotero
+2. Right-click → AI Butler → Summarize
+3. Summary added as Zotero note
+
+### Summary Templates
+- **Quick Summary** (1 paragraph): Core contribution + method + result
+- **Structured Summary**: Background / Method / Results / Limitations
+- **Executive Brief**: Who should read this and why
+- **Technical Deep-Dive**: Detailed methodology and math
+```
+
+### Key Finding Extraction
+
+```markdown
+### Extract structured information:
+- **Research question**: What problem does this paper address?
+- **Methodology**: What approach do the authors use?
+- **Key results**: What are the main findings?
+- **Contributions**: What is novel about this work?
+- **Limitations**: What are the acknowledged limitations?
+- **Future work**: What directions do the authors suggest?
+```
+
+### Paper Comparison
+
+```markdown
+### Compare multiple papers:
+1. Select 2+ papers in Zotero
+2. Right-click → AI Butler → Compare Papers
+3. Generates comparison table:
+   - Shared and unique contributions
+   - Methodological differences
+   - Performance comparison (if applicable)
+   - Complementary insights
+```
+
+### Q&A Mode
+
+```markdown
+### Ask questions about papers:
+1. Open paper in Zotero reader
+2. AI Butler sidebar → Ask a question
+3. Answers grounded in paper content with page references
+
+Example questions:
+- "What loss function do they use?"
+- "How does this compare to prior work?"
+- "What are the hyperparameters?"
+- "Explain equation 3 in simpler terms"
+```
+
+## Batch Processing
+
+```markdown
+### Summarize multiple papers:
+1. Select papers (or entire collection)
+2. Right-click → AI Butler → Batch Summarize
+3. Progress bar shows completion
+4. Each paper gets a summary note attached
+
+### Reading List Generation:
+1. Select collection
+2. AI Butler → Generate Reading Order
+3. Suggests optimal reading sequence based on:
+   - Citation relationships
+   - Conceptual dependencies
+   - Publication chronology
+```
+
+## Custom Prompts
+
+```markdown
+### Create custom analysis prompts:
+# In AI Butler preferences → Custom Prompts
+
+Prompt: "Systematic Review Extraction"
+Template: |
+  Extract the following from this paper:
+  1. Study design (RCT, cohort, etc.)
+  2. Sample size
+  3. Primary outcome
+  4. Effect size with CI
+  5. Risk of bias indicators
+  Format as structured JSON.
+```
+
+## Integration with Zotero Workflow
+
+```markdown
+### Combined Plugin Workflow
+1. **Zotero Connector** → Import paper
+2. **Zotero Sci-Hub** → Fetch PDF
+3. **AI Butler** → Generate summary note
+4. **Zotero Actions Tags** → Auto-tag based on summary
+5. **Notero** → Sync to Notion with summary
+6. **Better BibTeX** → Export citations for writing
+```
+
+## Use Cases
+
+1. **Rapid screening**: Quick summaries for literature triage
+2. **Paper comprehension**: Ask clarifying questions
+3. **Comparison studies**: Side-by-side paper analysis
+4. **Data extraction**: Structured information for systematic reviews
+5. **Reading preparation**: Generate briefings before journal club
+
+## References
+
+- [Zotero AI Butler GitHub](https://github.com/steven-jianhao-li/zotero-AI-Butler)
+- [Zotero Plugin Development](https://www.zotero.org/support/dev/client_coding/plugin_development)